Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 24576
    5. 8-RES_FS24576-JB
    6. 822
    Prev
    Next
    INDEX
    Explanations

    movements or actions involving cutting or shaping of physical objects

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs24576-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    288
    +0.14
    0.6%
    383
    +0.12
    0.5%
    213
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    383
    +0.14
    0.01
    699
    +0.12
    0.01
    288
    +0.10
    0.01
    Negative Logits
     McGr
    -0.68
     Mub
    -0.66
    BUS
    -0.64
    enez
    -0.64
     rainy
    -0.63
     Luxem
    -0.63
     Bruins
    -0.62
     Samar
    -0.62
     Lowry
    -0.61
     Forbes
    -0.61
    POSITIVE LOGITS
     carving
    1.07
     sculptures
    1.02
    smanship
    0.96
    resses
    0.90
     carved
    0.88
    pain
    0.85
     sculpt
    0.82
    ulas
    0.82
     carve
    0.81
    ember
    0.80
    Activations Density 0.025%

    No Known Activations